FDA clears ultrasound AI tool for accurate delivery-date prediction

An artificial intelligence-enabled tool capable of accurately predicting an expectant mother’s delivery date has received the U.S. Food and Drug Administration’s De Novo clearance. 

Ultrasound AI—a company that specializes in medical imaging AI applications—on Monday announced the clearance of its flagship Delivery Date AI technology. The product is a cloud-based software as a medical device that predicts delivery dates using ultrasound imaging alone. This could help to better prepare both patients and providers for potential complications, reducing the likelihood of preterm birth. 

It was trained on a diverse dataset of over 1 million ultrasound images and evaluated via a peer-reviewed study, published in the Journal of Maternal-Fetal & Neonatal Medicine. The study, which included nearly 6,000 patients, determined AI could achieve an accuracy of 0.92 R² value for predicting the day a mother would deliver her child using only standard ultrasound images. 

Delivery Date AI can be easily integrated into most ultrasound systems. Ultrasound AI indicates that installation takes just a few minutes and offers organizations scalability while also potentially reducing long-term costs by improving maternal outcomes. 

"Fetal development and delivery timing impact nearly every decision in obstetrics," Nathan Fox, MD, a board-certified OB-GYN, maternal fetal medicine specialist, and partner physician with Ultrasound AI, noted. "Delivery Date AI gives clinicians unprecedented insight into a pregnancy's progression, allowing us to make more informed decisions for how and when we intervene."

Learn more here.